Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ש
    2.16
    من
    2.05
    الإ
    1.98
    إ
    1.97
    ição
    1.93
    Aging
    1.90
    Т
    1.89
    Cuál
    1.73
    ições
    1.66
    غ
    1.66
    POSITIVE LOGITS
    ্পনিক
    1.72
    мб
    1.64
    ip
    1.55
    down
    1.51
     thiểu
    1.51
    ება
    1.45
     optima
    1.45
    𝒽
    1.45
     haunts
    1.41
     rechte
    1.41
    Act Density 0.075%

    No Known Activations